INDEX

Explanations

occurrences of the letter 'f' in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unge

-0.17

olu

-0.16

orda

-0.16

mÃ®

-0.16

zim

-0.16

unger

-0.15

athers

-0.15

 éĢ

-0.15

odi

-0.14

lej

-0.14

POSITIVE LOGITS

0.22

ava

0.18

ÐµÑģÐ°

0.16

çĲ

0.15

ester

0.15

iven

0.15

uala

0.14

AVA

0.14

 borderTop

0.14

icer

0.14

Activations Density 0.018%

occurrences of the letter 'f' in various contexts

No Comments

No Known Activations